Nova Pro vs Sarvam 105B

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Agentic
Coding
Multimodal & Grounded
Reasoning
Knowledge
Instruction Following
Multilingual
Mathematics

Nova Pro· Sarvam 105B

Quick Verdict

Pick Sarvam 105B if you want the stronger benchmark profile. Nova Pro only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Sarvam 105B is clearly ahead on the aggregate, 60 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Sarvam 105B's sharpest advantage is in mathematics, where it averages 92.3 against 41.1. The single biggest benchmark swing on the page is MMLU, 41% to 90.6%.

Sarvam 105B is the reasoning model in the pair, while Nova Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

Operational tradeoffs

ProviderAmazonSarvam
PricePricing unavailableFree*
Speed141 t/sN/A
TTFT0.81sN/A
Context128K128K

Decision framing

BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.

Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.

BenchmarkNova ProSarvam 105B
AgenticSarvam 105B wins
BrowseComp39%49.5%
OSWorld-Verified32%
CodingSarvam 105B wins
LiveCodeBench14%
SWE-bench Pro20%
LiveCodeBench v671.7%
SWE-bench Verified45%
Multimodal & Grounded
MMMU-Pro37%
OfficeQA Pro46%
Reasoning
MuSR37%
BBH63%
LongBench v251%
gpqaDiamond78.7%
hle11.2%
KnowledgeSarvam 105B wins
MMLU41%90.6%
GPQA40%
SuperGPQA38%
MMLU-Pro53%81.7%
HLE4%
FrontierScience41%
SimpleQA39%
Instruction FollowingSarvam 105B wins
IFEval66%84.8%
Multilingual
MGSM61%
MMLU-ProX60%
MathematicsSarvam 105B wins
AIME 202341%
AIME 202443%
AIME 202542%88.3%
HMMT Feb 202337%
HMMT Feb 202439%
HMMT Feb 202538%
BRUMO 202540%
MATH-50098.6%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
Frequently Asked Questions (6)

Which is better, Nova Pro or Sarvam 105B?

Sarvam 105B is ahead overall, 60 to 33. The biggest single separator in this matchup is MMLU, where the scores are 41% and 90.6%.

Which is better for knowledge tasks, Nova Pro or Sarvam 105B?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 34.4. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Nova Pro or Sarvam 105B?

Sarvam 105B has the edge for coding in this comparison, averaging 45 versus 17. Nova Pro stays close enough that the answer can still flip depending on your workload.

Which is better for math, Nova Pro or Sarvam 105B?

Sarvam 105B has the edge for math in this comparison, averaging 92.3 versus 41.1. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Nova Pro or Sarvam 105B?

Sarvam 105B has the edge for agentic tasks in this comparison, averaging 49.5 versus 34.9. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for instruction following, Nova Pro or Sarvam 105B?

Sarvam 105B has the edge for instruction following in this comparison, averaging 84.8 versus 66. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Last updated: April 3, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.